Determining respiratory rate from photoplethysmogram and electrocardiogram signals using respiratory quality indices and neural networks.

Stephanie Baker,Wei Xiang,Ian Atkinson,Chi-Hua Chen

doi:10.1371/journal.pone.0249843

Abstract

Continuous and non-invasive respiratory rate (RR) monitoring would significantly improve patient outcomes. Currently, RR is under-recorded in clinical environments and is often measured by manually counting breaths. In this work, we investigate the use of respiratory signal quality quantification and several neural network (NN) structures for improved RR estimation. We extract respiratory modulation signals from the electrocardiogram (ECG) and photoplethysmogram (PPG) signals, and calculate a possible RR from each extracted signal. We develop a straightforward and efficient respiratory quality index (RQI) scheme that determines the quality of each moonddulation-extracted respiration signal. We then develop NNs for the estimation of RR, using estimated RRs and their corresponding quality index as input features. We determine that calculating RQIs for modulation-extracted RRs decreased the mean absolute error (MAE) of our NNs by up to 38.17%. When trained and tested using 60-sec waveform segments, the proposed scheme achieved an MAE of 0.638 breaths per minute. Based on these results, our scheme could be readily implemented into non-invasive wearable devices for continuous RR measurement in many healthcare applications.

Highlights

Respiratory rate (RR) is a fundamental physiological parameter, and abnormality in this vital sign is one of the earliest indicators of critical illness
Bland Altman analysis was conducted by calculating the bias or mean difference (MD), the difference or width between the limits of agreement (LOAs), and the percentage of results that fall between said LOAs
The inclusion of features calculated based on our proposed respiratory quality index (RQI) scheme greatly improves the performance of the bidirectional long short-term memory (BiLSTM) neural network

Summary

Introduction

Respiratory rate (RR) is a fundamental physiological parameter, and abnormality in this vital sign is one of the earliest indicators of critical illness. One recent study found that elevated respiratory rate was a key predictor of clinical deterioration within 48 hours of discharge from the emergency department [1]. Another classical study determined that the occurrence of at least one RR 27 breaths per minute (BrPM) in a 72 hour period was a strong predictor of cardiac arrest [2]. Elevated RR has been linked to increased mortality [3], while relative changes in RR have been shown to indicate patient stability [4].

Objectives

Methods

Results

Conclusion